CN113567342A - Transparent object defect detection method and device - Google Patents
Transparent object defect detection method and device Download PDFInfo
- Publication number
- CN113567342A CN113567342A CN202110960438.4A CN202110960438A CN113567342A CN 113567342 A CN113567342 A CN 113567342A CN 202110960438 A CN202110960438 A CN 202110960438A CN 113567342 A CN113567342 A CN 113567342A
- Authority
- CN
- China
- Prior art keywords
- grid
- transparent object
- light source
- image
- tested
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 68
- 238000001514 detection method Methods 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 26
- 230000002950 deficient Effects 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 abstract description 3
- 230000001678 irradiating effect Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000002834 transmittance Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000037303 wrinkles Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/958—Inspecting transparent materials or objects, e.g. windscreens
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
本发明涉及一种透明物缺陷检测方法及装置。本发明提供的检测方法包括：采用网格光源照射待测透明物；获取待测透明物的图像；根据图像判定待测透明物是否有缺陷。本发明提供的检测装置包括网格光源、工业相机及控制中心；网格光源用于照射待测透明物；工业相机与控制中心相连，用于获取待测透明物的图像；控制中心接收工业相机获取的图像并根据需要对图像进行显示或处理。本发明通过采用网格光源照射待测透明物，如果待测透明物存在缺陷，就会使得获取的待测透明物的图像中的网格图案出现变形或者移位，从而快速、直观地判定待测透明物是否有缺陷，降低检测成本，提高检测效率。
The invention relates to a transparent object defect detection method and device. The detection method provided by the invention includes: using a grid light source to illuminate the transparent object to be tested; acquiring an image of the transparent object to be tested; and determining whether the transparent object to be tested is defective according to the image. The detection device provided by the invention includes a grid light source, an industrial camera and a control center; the grid light source is used to illuminate the transparent object to be measured; the industrial camera is connected to the control center for acquiring the image of the transparent object to be measured; the control center receives the industrial camera Acquire the image and display or process the image as needed. The invention uses a grid light source to illuminate the transparent object to be tested. If the transparent object to be tested has defects, the grid pattern in the obtained image of the transparent object to be tested will be deformed or displaced, so as to quickly and intuitively determine the transparent object to be tested. Detect whether transparent objects are defective, reduce inspection costs, and improve inspection efficiency.
Description
Technical Field
The invention relates to an industrial detection technology, in particular to a method and a device for detecting defects of a transparent object.
Background
Due to the high-transmittance optical characteristics of the transparent product, the defect characteristics of the surface of the transparent product, particularly non-foreign body defects such as unevenness of a mobile phone screen, wrinkled oil bubbles of a glass bottle and the like are difficult to observe. These defects do not block light or cause a large amount of reflection, but are the same as surrounding materials and have high light transmittance, so that the light is integrated with the surrounding and is not easy to distinguish.
The defects are difficult to detect by visual equipment, even if the defects are detected manually, the defects are observed at a plurality of angles, and the defects can be seen only at a certain special angle, so that the omission ratio is particularly high.
Disclosure of Invention
The invention provides a transparent object defect detection method and device with low cost and capability of reducing the omission factor, aiming at the problems of high detection cost and high omission factor of the existing transparent product.
In a first aspect, the present invention provides a transparency defect detecting method, including:
irradiating the transparent object to be detected by adopting a grid light source;
acquiring an image of a transparent object to be detected;
and judging whether the transparent object to be detected has defects according to the image.
By adopting the grid light source to irradiate the transparent object to be detected, if the transparent object to be detected has defects, the grid patterns in the acquired image of the transparent object to be detected are deformed or shifted, so that whether the transparent object to be detected has defects or not is judged quickly and visually, the detection cost is reduced, and the detection efficiency is improved.
Further, the grid light source employs a planar light source covered with a grid film, or a display screen displaying a grid pattern.
The planar light source covered with the grid film is adopted, so that the cost is low and the implementation is convenient; the display screen with the grid patterns is adopted, and the patterns are adjusted simply and efficiently.
Further, the grid pattern of the grid film or the grid pattern displayed by the display screen is one of grid, horizontal and vertical stripes, oblique stripes or dot matrix patterns.
The grid pattern can be selected according to the type of the defect to be detected, so that the defect to be detected can be more clearly shown.
Further, the grid pattern is adjustable.
According to the defect characteristics, the grid pattern is adjusted, for example, the thickness, the interval, the size of the single-point pattern in the dot matrix and the like are changed, so that the defect is more obvious and is easy to distinguish.
Further, an industrial camera is adopted to obtain an image of the transparent object to be measured.
And an industrial camera is adopted for shooting, so that images can be better displayed and analyzed in the later period.
In a second aspect, the invention provides a transparency defect detecting device, which comprises a grid light source, an industrial camera and a control center; the grid light source is used for irradiating the transparent object to be detected; the industrial camera is connected with the control center and used for acquiring an image of the transparent object to be detected; the control center receives images acquired by the industrial cameras and displays or processes the images as needed.
The defects of the transparent object to be detected are detected by the grid light source and the industrial camera in cooperation with a visual detection program in the control center, so that the method is rapid and intuitive, the detection cost is low, and the detection efficiency is high; and the transparent object can be detected on line in time, so that the detection precision and accuracy are improved.
Further, the grid light source employs a planar light source covered with a grid film, or a display screen displaying a grid pattern.
The planar light source covered with the grid film is adopted, so that the cost is low and the implementation is convenient; the display screen with the grid patterns is adopted, and the patterns are adjusted simply and efficiently.
Further, the grid pattern of the grid film or the grid pattern displayed by the display screen is one of grid, horizontal and vertical stripes, oblique stripes or dot matrix patterns.
The grid pattern can be selected according to the type of the defect to be detected, so that the defect to be detected can be more clearly shown.
Further, the grid pattern is adjustable.
By adjusting the grid pattern, whether the transparent object to be detected has defects can be more easily judged.
Further, the control center processes the image and selects a deep learning method to extract the defects, or calculates the shape change and/or gray change of the grid by a machine vision method to confirm the position and/or size of the defects.
The control center processes the image by adopting different methods, and can select corresponding methods according to different requirements, thereby improving the application range of the detection device.
Drawings
FIG. 1 is a schematic flow chart of a transparency defect detection method according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a transparency defect inspection apparatus according to an embodiment of the present invention;
FIGS. 3-4 are schematic diagrams of two grid patterns of a grid light source;
fig. 5-7 are images of defective vials taken using the apparatus of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
The invention provides a transparency defect detection method, which is used for detecting whether a transparency has defects.
FIG. 1 is a flow chart of an alternative embodiment of the transparency defect detection method.
As shown in fig. 1, the method for detecting the defects of the transparent object comprises the following steps:
s100, irradiating the transparent object to be detected by adopting a grid light source;
s200, acquiring an image of a transparent object to be detected;
s300, judging whether the transparent object to be detected has defects according to the image.
The principle of the method is as follows: when the grid light source is adopted to irradiate the transparent object to be detected, the light of the transparent object to be detected is bent due to the characteristics of the surface thickness, the contour, the wrinkles and the like of the transparent object to be detected, so that the grid pattern in the shot image is distorted and deformed or a black and white area is shifted, and the defects on the transparent object to be detected are obvious.
By adopting the grid light source to irradiate the transparent object to be detected, if the transparent object to be detected has defects, the grid patterns in the acquired image of the transparent object to be detected are deformed or shifted, so that whether the transparent object to be detected has defects or not is judged quickly and visually, the detection cost is reduced, and the detection efficiency is improved.
Alternatively, in step S100, the grid light source employs a planar light source covered with a grid film, or a display screen displaying a grid pattern. The planar light source can adopt an LED planar light source, and the display screen can adopt an LED display screen or a liquid crystal display screen.
The planar light source covered with the grid film is adopted, so that the cost is low and the implementation is convenient; the display screen with the grid patterns is adopted, and the patterns are adjusted simply and efficiently.
Optionally, the grid pattern of the grid film or the grid pattern displayed by the display screen is one of a grid, a horizontal stripe, a vertical stripe, a diagonal stripe or a dot matrix pattern.
The grid pattern can be selected according to the type of the defect to be detected, so that the defect to be detected can be more clearly shown.
Optionally, the grid pattern is adjustable. The method can be suitable for detecting defects with different sizes and characteristics by adjusting the thickness and the interval size of the stripes in the grid pattern and the size of the single-point pattern in the dot matrix. If the light source is used for the display screen, the grid patterns displayed by the display screen can be directly switched to adapt to the detection of different defects.
The grid pattern is adjusted according to the defect characteristics, so that the defects are more obvious and are easy to distinguish.
Optionally, in step S200, an industrial camera is used to acquire an image of the transparent object to be measured. The industrial camera may employ a CCD camera or a CMOS camera.
And an industrial camera is adopted for shooting, so that images can be better displayed and analyzed in the later period.
As shown in fig. 2, the present invention further provides a device 800 for detecting defects of transparencies, comprising a grid light source 400, an industrial camera 600 and a control center 700; the grid light source 400 is used for irradiating the transparent object 500 to be detected; the industrial camera 600 is connected with the control center 700 and is used for acquiring an image of the transparent object 500 to be detected; the control center 700 receives images acquired by the industrial camera 600 and displays or processes the images as needed. Alternatively, the control center 700 may employ an industrial personal computer or a control module with image display or processing.
The defects of the transparent object 500 to be detected are detected through the grid light source 400 and the industrial camera 600 and by matching with a visual detection program in the control center 700, so that the detection is rapid and intuitive, the detection cost is low, and the detection efficiency is high; and the transparent object can be detected on line in time, so that the detection precision and accuracy are improved.
Alternatively, the grid light source 400 employs a planar light source covered with a grid film, or a display screen displaying a grid pattern.
The planar light source covered with the grid film is adopted, so that the cost is low and the implementation is convenient; the display screen with the grid patterns is adopted, and the patterns are adjusted simply and efficiently.
Optionally, the grid pattern of the grid film or the grid pattern displayed by the display screen is one of grid, horizontal and vertical stripes or diagonal stripes, as shown in fig. 3 and 4.
The grid pattern can be selected according to the type of the defect to be detected, so that the defect to be detected can be more clearly shown.
Optionally, the grid pattern is adjustable.
By adjusting the grid pattern, it is easier to determine whether the transparency 500 under test has defects. By switching the scale of the grid pattern in the light source, the defects with different scales and characteristics can be detected, and various defects can be detected at the same station.
Optionally, the control center 700 processes the image by using a deep learning method to extract the defect, or calculates the shape change and/or the gray change of the grid by using a machine vision method to confirm the position and/or the size of the defect.
The control center 700 processes the image by adopting different methods, and can select corresponding methods according to different requirements, so that the application range of the detection device is widened.
FIGS. 5-7 are graphs showing the results of inspecting transparency defects using the present invention, as shown in the rectangular boxes. As can be seen from the figure, the grid pattern of the grid light source is deformed on the transparent object, so that the defect can be clearly seen and detected by a visual program.
The device 800 for detecting the defects of the transparent objects does not need to detect at a plurality of angles and the front and the back because of the adoption of the grid light source 400, thereby greatly saving detection stations, reducing the complexity of equipment and improving the detection efficiency.
The invention has been described above with a certain degree of particularity. It will be understood by those of ordinary skill in the art that the description of the embodiments is merely exemplary and that all changes that come within the true spirit and scope of the invention are desired to be protected. The scope of the invention is defined by the appended claims rather than by the foregoing description of the embodiments.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110960438.4A CN113567342A (en) | 2021-08-20 | 2021-08-20 | Transparent object defect detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110960438.4A CN113567342A (en) | 2021-08-20 | 2021-08-20 | Transparent object defect detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113567342A true CN113567342A (en) | 2021-10-29 |
Family
ID=78172304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110960438.4A Pending CN113567342A (en) | 2021-08-20 | 2021-08-20 | Transparent object defect detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113567342A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111505023A (en) * | 2020-05-08 | 2020-08-07 | 苏州英士派克光电科技有限公司 | Optical detection method for transparent material |
| CN115165920A (en) * | 2022-09-06 | 2022-10-11 | 南昌昂坤半导体设备有限公司 | A three-dimensional defect detection method and detection equipment |
| CN117677838A (en) * | 2022-02-16 | 2024-03-08 | 卡尔蔡司光学国际有限公司 | Test equipment and test methods |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103454287A (en) * | 2013-09-05 | 2013-12-18 | 深圳市维图视技术有限公司 | Glass tube defect visual detection method and device |
| CN103472072A (en) * | 2013-09-09 | 2013-12-25 | 深圳市维图视技术有限公司 | Novel visual inspection method and device for glass tube defects |
| CN105241400A (en) * | 2015-11-09 | 2016-01-13 | 福建农林大学 | Glass flatness detection method and device |
| CN109030495A (en) * | 2018-06-26 | 2018-12-18 | 大连鉴影光学科技有限公司 | A kind of optical element defect inspection method based on machine vision technique |
| CN110849911A (en) * | 2019-11-25 | 2020-02-28 | 厦门大学 | Glass defect image acquisition device, glass defect detection equipment and detection method |
| CN215812367U (en) * | 2021-08-20 | 2022-02-11 | 安徽顺鼎阿泰克科技有限公司 | Transparent object defect detection device |
-
2021
- 2021-08-20 CN CN202110960438.4A patent/CN113567342A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103454287A (en) * | 2013-09-05 | 2013-12-18 | 深圳市维图视技术有限公司 | Glass tube defect visual detection method and device |
| CN103472072A (en) * | 2013-09-09 | 2013-12-25 | 深圳市维图视技术有限公司 | Novel visual inspection method and device for glass tube defects |
| CN105241400A (en) * | 2015-11-09 | 2016-01-13 | 福建农林大学 | Glass flatness detection method and device |
| CN109030495A (en) * | 2018-06-26 | 2018-12-18 | 大连鉴影光学科技有限公司 | A kind of optical element defect inspection method based on machine vision technique |
| CN110849911A (en) * | 2019-11-25 | 2020-02-28 | 厦门大学 | Glass defect image acquisition device, glass defect detection equipment and detection method |
| CN215812367U (en) * | 2021-08-20 | 2022-02-11 | 安徽顺鼎阿泰克科技有限公司 | Transparent object defect detection device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111505023A (en) * | 2020-05-08 | 2020-08-07 | 苏州英士派克光电科技有限公司 | Optical detection method for transparent material |
| CN117677838A (en) * | 2022-02-16 | 2024-03-08 | 卡尔蔡司光学国际有限公司 | Test equipment and test methods |
| CN115165920A (en) * | 2022-09-06 | 2022-10-11 | 南昌昂坤半导体设备有限公司 | A three-dimensional defect detection method and detection equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113567342A (en) | Transparent object defect detection method and device | |
| CN111693549B (en) | A kind of mobile phone cover glass defect detection and classification method | |
| CN106705897B (en) | Defect detection method of curved glass panel for curved electronic display | |
| Rosati et al. | Real-time defect detection on highly reflective curved surfaces | |
| CN101738401A (en) | Defect inspection device and defect inspection method | |
| CN102590221A (en) | Apparent defect detecting system and detecting method of polarizer | |
| CN109406529B (en) | Performance adjusting method of AOI defect detection system | |
| CA2567095C (en) | A method for inspecting transparent or reflective elements | |
| CN105911724B (en) | Determine the method and apparatus of the intensity of illumination for detection and optical detecting method and device | |
| CN107664644A (en) | A kind of apparent automatic detection device of object based on machine vision and method | |
| TWI583932B (en) | Device for measuring optical quality of lenses | |
| CN104990942A (en) | Detection system and method of defected vision caused by transparent glass containers | |
| Deng et al. | A novel imaging-enhancement-based inspection method for transparent aesthetic defects in a polymeric polarizer | |
| CN113008524A (en) | Screen light leakage detection method and device | |
| JPWO2007132925A1 (en) | Surface inspection device | |
| CN215812367U (en) | Transparent object defect detection device | |
| TW201925746A (en) | Defect inspection device and defect inspection method | |
| JP3899915B2 (en) | Optical strain evaluation method and evaluation apparatus | |
| CN104848808B (en) | A kind of Surface Roughness Detecting Method and equipment | |
| CN101556141A (en) | Fourier transformation method for measuring irregular slit width and device | |
| CN109785290A (en) | Normalized steel plate defect detection method is shone based on local light | |
| CN110441331B (en) | Glass optical distortion detection system and method | |
| CN116993658B (en) | A method for accurately detecting OCA lamination accuracy | |
| CN115345853A (en) | Real-time measurement method, system, device and storage medium for multiple field of view MTF of lens | |
| JP2020003343A (en) | Defect inspection device and defect inspection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211029 |
|
| RJ01 | Rejection of invention patent application after publication |